Multiple Instance Choquet integral for classifier fusion

The Multiple Instance Choquet integral (MICI) for classifier fusion and an evolutionary algorithm for parameter estimation is presented. The Choquet integral has a long history of providing an effective framework for non-linear fusion. However, previous methods to learn an appropriate measure for the Choquet integral required accurate and precise training labels. In many applications, data-point specific labels are unavailable and infeasible to obtain. The proposed MICI algorithm allows for training with uncertain labels in which class labels are provided for sets of data points (i.e., “bags”) instead of individual data points (i.e., “instances”). The proposed algorithm is able to fuse multiple two-class classifier outputs by learning a monotonic and normalized fuzzy measure from uncertain training labels using an evolutionary algorithm. It produces enhanced classification performance by computing Choquet integral with the learned fuzzy measure. Results on both simulated and real hyperspectral data are presented in the paper.

[1]  Xiaoli Yu,et al.  Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution , 1990, IEEE Trans. Acoust. Speech Signal Process..

[2]  James M. Keller,et al.  Learning Fuzzy-Valued Fuzzy Measures for the Fuzzy-Valued Sugeno Fuzzy Integral , 2010, IPMU.

[3]  Louis L. Scharf,et al.  The adaptive coherence estimator: a uniformly most-powerful-invariant adaptive detection statistic , 2005, IEEE Transactions on Signal Processing.

[4]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[5]  G. Choquet Theory of capacities , 1954 .

[6]  Janusz Kacprzyk,et al.  Beyond two: theory and applications of multiple-valued logic , 2003 .

[7]  Timothy C. Havens,et al.  Regularization-based learning of the Choquet integral , 2014, 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

[8]  Michel Grabisch Modelling data by the Choquet integral , 2003 .

[9]  Dong Chen,et al.  Research on intelligent fault diagnosis method for complex equipment based on decision-level fusion , 2010, 2010 International Conference on Machine Learning and Cybernetics.

[10]  D. Timmerman,et al.  Automated classification of static ultrasound images of ovarian tumours based on decision level fusion , 2014, 2014 6th Computer Science and Electronic Engineering Conference (CEEC).

[11]  Ma Wenjun,et al.  Research on detection of prostate cancer MR images based on information fusion , 2014, 2014 12th International Conference on Signal Processing (ICSP).

[12]  Brian A. Baertlein,et al.  Feature-Level and Decision-Level Fusion of Noncoincidently Sampled Sensors for Land Mine Detection , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Qian Du,et al.  Decision Fusion on Supervised and Unsupervised Classifiers for Hyperspectral Imagery , 2010, IEEE Geoscience and Remote Sensing Letters.

[14]  M. Grabisch The application of fuzzy integrals in multicriteria decision making , 1996 .

[15]  Paul D. Gader,et al.  Experiments in predictive sensor fusion , 2001, SPIE Defense + Commercial Sensing.

[16]  Alex Lascarides,et al.  Computational Intelligence for Knowledge-Based Systems Design , 2010 .

[17]  Paul D. Gader,et al.  Fusion of handwritten word classifiers , 1996, Pattern Recognit. Lett..

[18]  Paul D. Gader,et al.  Minimum Classification Error Training for Choquet Integrals With Applications to Landmine Detection , 2008, IEEE Transactions on Fuzzy Systems.

[19]  L.L. Scharf,et al.  Adaptive matched subspace detectors and adaptive coherence estimators , 1996, Conference Record of The Thirtieth Asilomar Conference on Signals, Systems and Computers.

[20]  N. L. Johnson,et al.  Continuous Univariate Distributions. , 1995 .

[21]  Christophe Labreuche,et al.  The Choquet integral for the aggregation of interval scales in multicriteria decision making , 2003, Fuzzy Sets Syst..

[22]  Tomás Lozano-Pérez,et al.  A Framework for Multiple-Instance Learning , 1997, NIPS.

[23]  Changzhe Jiao,et al.  Functions of Multiple Instances for Learning Target Signatures , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[24]  James M. Keller,et al.  Fuzzy Models and Algorithms for Pattern Recognition and Image Processing , 1999 .

[25]  Michael A. Zatman,et al.  A computationally efficient two-step implementation of the GLRT , 2000, IEEE Trans. Signal Process..

[26]  Paul D. Gader,et al.  New fuzzy set tools to aid in predictive sensor fusion , 2000, Defense, Security, and Sensing.

[27]  菅野 道夫,et al.  Theory of fuzzy integrals and its applications , 1975 .

[28]  Peijun Du,et al.  Hyperspectral remote sensing image classification based on decision level fusion , 2011 .

[29]  Paul D. Gader,et al.  Generalized Choquet fuzzy integral fusion , 2002, Inf. Fusion.

[30]  Farhad Samadzadegan,et al.  Object Recognition Based on the Context Aware Decision-Level Fusion in Multiviews Imagery , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[31]  Paul D. Gader,et al.  Context-Dependent Multisensor Fusion and Its Application to Land Mine Detection , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[32]  Li Chen,et al.  Research on detection of prostate cancer MR images based on information fusion , 2014 .

[33]  D. Ruta,et al.  An Overview of Classifier Fusion Methods , 2000 .

[34]  Jon Atli Benediktsson,et al.  Fusion of Support Vector Machines for Classification of Multisensor Data , 2007, IEEE Transactions on Geoscience and Remote Sensing.